Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare generic hints (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds the genuinely useful behavior: it clears all three block categories at once, and spam-complaint blocks require a consent record as proof. It does not say whether clearing removes the underlying event history or what the response contains, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the action and scope, then the prerequisite, then the sibling routing. No filler and nothing repeated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-required-parameter mutation tool with no output schema and sparse annotations, the description covers the consent gating and the sibling boundary well, but says nothing about the 'reason' argument, whether unblocking affects past send/bounce records, or what a successful call returns. Adequate, not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% — only 'consent' and 'consented_at' are documented. The description compensates partially by explaining what consent means in practice ('proof the person asked') and when it is required, but it never explains the 'reason' parameter or the nested wording/ip_address/user_agent fields, leaving the low-coverage gap only half filled.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+object: 'Clear the bounces, spam complaints and manual blocks recorded for an address so far.' That names both the action and the exact state being cleared, and the final sentence distinguishes it from resubscribe_email, so an agent can separate it from block_email/unsubscribe_email without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a precondition ('An address that reported spam needs consent (proof the person asked)') and an explicit exclusion with an alternative ('An unsubscribe is not cleared here; use resubscribe_email'). That is when-to-use, prerequisite, and when-not-to-use in three sentences.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.